Skip to content
Sagan

Paper

AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees

Unreadunread

AI summary

arXiv:2605. 19260v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iteration step.